ZEN ES Benchmark from french hardware Magazine

Page 22 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

AtenRa

Lifer
Feb 2, 2009
14,000
3,357
136
I am waiting for AMD to demo Turbo Boost at CES 2017 to really rub it in to the people who were making authoritative statements about Zen being a low frequency design. ;)

First it was ZEN will be a Cat core (small) because AMD doesnt have the $ for R&D
Then it was ZEN IPC will be close to SandyBridge because AMD bla bla bla
Then it was ZEN will have low clocks because of High IPC and shitty GloFo 14nm LPP

Im not saying 5GHz will be true or not but even IF 8C 16T RYZEN can OC to 4.5GHz with BDW IPC, then it will be the best come back of AMD in the last 20 years because of their current worst financial state they are in .
 
Last edited:

bjt2

Senior member
Sep 11, 2016
784
180
86
Lol confirmed. Wake me up if you have a screenshot running Prime95 AVX2 30 min+ on air with all cores enabled from a trustable guy.

There are lot of CPUz screen. All these should be taken with a grain of salt and subtract some few hundreds Mhz to get a daily use frequency. 5GHz on air with huge heat sink and one core active can mean 4.6-4.7 stable OC on all cores. Could also mean that if you let do the job to the auto OC maybe you have 4.3-4.4 on all cores, but also 4.7-4.8 on one core...

Anyway this is an A0 ES and Charlie said that they are at least at step A3... And B&C teased to higher clocks on newer steps, so... I think that at least 4.5 stable can be obtained...
 

F-Rex

Junior Member
Aug 11, 2016
19
5
81
As I said before, there are no Ax parts. Just A0x. Therefore you should advance in the alphabet ;)
If someone says there is, he is either lying or being lied to.
So according to you, amd did not made a single Mask revision since first zen samples got out of the fab 6 months ago.
You work at toppan?
 

raghu78

Diamond Member
Aug 23, 2012
4,093
1,475
136
And this estimation was based on the official statement from?

The age old mantra for any company is to underpromise and overdeliver. I think AMD have done a good job with managing expectations given Zen is a clean sheet design and there are huge risks with such a venture. But the problem is when people like you make authoritative statements about Zen without having a clue about the actual product. Anyway I want AMD to succeed phenomenally so that we as consumers see very strong competition in both CPU and GPU markets and benefit from it. I think Zen and Vega look like they will put AMD back in business and on the road to recovery. I am eager to see what AMD has cooked up with Zen/Vega and look forward to their successors Zen+ / Navi. One thing is for sure the next generation of game consoles will not be starved for CPU power. :)
 

KTE

Senior member
May 26, 2016
478
130
76
FI at 0.3W dynamic power there will be 90mW added leakage for 28nm SLP and 18mW leakage for 14nm LPP.

In comparison the improvement due to higher speed is almost 3x, that is, at 300mW dynamic power a A57 will clock at 2.4GHz with 14nm and 1.4GHz with low power 28nm SLP.

Wich also mean that at 1.4GHz 14nm LPP will use only 100mW dynamic power, as you can see lower Ioff, although noticeable, is a second order parameter in the whole improvement.

guess that he can repeat the same things ad nauseam, even if they are substancied they wont enter in some brains that hang by here, so he s not exactly the one who is to blame for his own posts redundancies, indeed you have an exemple with my explanation about Ioff impact, several posts were necessary to explain the obvious...
Wherever Sonic goes, Tails shows up. Tick Tock
If other members here keep saying things that don't fit the data and reasoning i was giving here, i keep repeating, with other words, because maybe i was not clear the other times i said that.

If you say X, without proof, and i have proof that X is false, why i must stay quiet?

Keep making unsupported claims and I will continue to respond with facts.
Continuing to make unsupported claims will not make them true. And after CES, this game will CEaSe... Because the truth will be out..

Spreading false or unsupported informations is what leads to big surprised guys: no one ever expected 3.4GHz+ base clocks for Zen. Why? Because there are dozens of persons shouting sentences like "AMD can't do a chip with higher clock of INTEL's because GF process is worse than INTEL's", completely forgetting FO4. And Excavator's clock and overclocks on a 28nm BULK process with HDL libraries are a perfect example. 4 base, 4.3 turbo and 4.9 air OC is not bad. And this was due only to FO4. Because even Haswell on 22nm did not reach the clocks of A12 9800. And Excavator reached this also in 65W TDP! What else can be? 28nm BULK better than 22nm FinFet? Obviously no!
We have already reached better clock than BWE: 6900K has 3.2Ghz base and RyZen will have more than 3.4GHz base clock. With less TDP. On a worse process. How is this possible? Is low power GF process better than high power INTEL process? Or mabybe it's the FO4? We have indication that the FO4 will be low: 19 stage integer pipeline, 6xone way iteger scheduler, 2 stages floating point scheduler and Keller statements...
More and more claims and negative, baseless allegations, no evidence, no valid reasoning... I am just expected to believe and not question, or the boogy gang will get me. Reoccuring theme here.

Keep going. So far, your claims relating XV/ARM/GF/FO4/Zen process (which I questioned) have come out completely wrong. Because as I said, your reasoning is 1+3=10. No accounting for the remaining 6, oh no, how dare anyone. Technically, it does not hold up, except for some huge doze of hope+faith. When I questioned you on specifics, you couldn't answer, yet you still expect me to blindly believe your way as the only correct fact. So because I refuse to convert to your beliefs, I am anti-AMD. Right.

Wait till launch, and I will make sure I reply to these posts of yours point by point. It'll be a nice, juicy discussion... Pun intended. We can take the discussion to RWT if you prefer. David always did want me to post there, but juans elder bro savantu stopped me

BTW, only you have been defensively claiming things... I've only objected to you, so far.

Guys like you/juan make AMD look so bad on new product launches by bringing false unreasonable hope to fans using pseudoscience. No sense of staying reasonable. Both extreme opposites on the curve, archenemies.

I speak as an AMD fan here - but not fanatic.

BRAD, why don't you start posting in this thread since the topics about your favorite Tejas now

Sent from HTC 10
(Opinions are own)
 
  • Like
Reactions: Arachnotronic

The Stilt

Golden Member
Dec 5, 2015
1,709
3,057
106
So according to you, amd did not made a single Mask revision since first zen samples got out of the fab 6 months ago.
You work at toppan?

You simply didn't read or just didn't understand what I wrote in the same post you quoted?

Also I'm pretty sure Fab 6 hasn't put out anything Zen related, for obvious reasons...

No, I don't work for Toppan.
 

The Stilt

Golden Member
Dec 5, 2015
1,709
3,057
106
The age old mantra for any company is to underpromise and overdeliver. I think AMD have done a good job with managing expectations given Zen is a clean sheet design and there are huge risks with such a venture. But the problem is when people like you make authoritative statements about Zen without having a clue about the actual product. Anyway I want AMD to succeed phenomenally so that we as consumers see very strong competition in both CPU and GPU markets and benefit from it. I think Zen and Vega look like they will put AMD back in business and on the road to recovery. I am eager to see what AMD has cooked up with Zen/Vega and look forward to their successors Zen+ / Navi. One thing is for sure the next generation of game consoles will not be starved for CPU power. :)

Wrong.
AMD didn't do good job with Zen.
They did phenominal job and delivered more than they promised, allegedly of course ;)
 
  • Like
Reactions: KTE

KTE

Senior member
May 26, 2016
478
130
76
Was that a question?

EDIT: Let's revisit your statement after the product has been launched ;)

Also could you provide few examples about the things I was wrong about?
Charlie had been wrong many times before in the Phenom days...

But I'm pretty certain it will not be A0 step for launch.

Also, chew/Stilt were like the primary most reliable sources back with Barcelona/Shanghai/Istanbul among immense FUD. I'm sure inf64 remembers

My bad i think that if zen goes like a Ferrari, it will cost like a Ferrari... But will draw same power as a Fiat, it seems...
I, too, own a Mclaren P1 1200hp that sips juice at 120 miles per gallon!!

Sent from HTC 10
(Opinions are own)
 
Last edited:

Maverick177

Senior member
Mar 11, 2016
411
70
91
And this estimation was based on the official statement from?

Was that a question?

EDIT: Let's revisit your statement after the product has been launched ;)

Also could you provide few examples about the things I was wrong about?

Here's your post from late Aug this year:

https://forums.anandtech.com/thread...ecture-details.2465645/page-113#post-38444592

I expect it to vary heavily depending on the workload, however the average should be pretty well matched with Sandy & Ivy Bridge.

I have nothing against you but don't you think you are not in the moral high ground here?
 
Last edited:
  • Like
Reactions: raghu78

The Stilt

Golden Member
Dec 5, 2015
1,709
3,057
106
Nice to see you acknowledge the multiple revisions but as A00 , A01, A02, A03

:D
That's not what I meant either...
The stepping format for AMD is major, minor, node. Generally node is not public information or otherwise disclosed anywhere. For example Vishera had several nodes (C0x) and back in the days of glory (i.e own fabs) two character node marker was required...
A0c is the most recent A0 stepping based spin, however not necessarily the most recent stepping in terms of major and minor...
 

KTE

Senior member
May 26, 2016
478
130
76
So it's B0 or similar.
He is saying they are revisions of the same major stepping, A0.

Smaller revs have existed in previous AMD nodes too, but they weren't mostly public knowledge.

Sent from HTC 10
(Opinions are own)
 

raghu78

Diamond Member
Aug 23, 2012
4,093
1,475
136
Here's your post from late Aug this year:

https://forums.anandtech.com/thread...ecture-details.2465645/page-113#post-38444592

I have nothing against you but don't you think you are not in the moral high ground here?

Well said. There have been too many people who wrote off AMD and never gave them a chance at competing with Intel. I have been an eternal underdog supporter and thus have held on to the belief that AMD will turnaround their fortunes from the Bulldozer disaster. But the last 4 years have been very painful to watch from AMD's point of view. Their revenues slipping badly and losses mounting and the GPU division too suffering from reduced R&D. But its admirable that AMD did what they had to and made sure Zen got the resources it needed. AMD did not compromise on their goal of designing a high performance CPU architecture and re entering the high performance compute and server market. I hope Zen knocks it out of the park on every aspect - IPC, ST and MT perf, max OC, perf/watt. AMD need a home run.
 

The Stilt

Golden Member
Dec 5, 2015
1,709
3,057
106
  • Like
Reactions: Phynaz

bjt2

Senior member
Sep 11, 2016
784
180
86
Wherever Sonic goes, Tails shows up. Tick Tock

More and more claims and negative, baseless allegations, no evidence, no valid reasoning... I am just expected to believe and not question, or the boogy gang will get me. Reoccuring theme here.

Keep going. So far, your claims relating XV/ARM/GF/FO4/Zen process (which I questioned) have come out completely wrong. Because as I said, your reasoning is 1+3=10. No accounting for the remaining 6, oh no, how dare anyone. Technically, it does not hold up, except for some huge doze of hope+faith. When I questioned you on specifics, you couldn't answer, yet you still expect me to blindly believe your way as the only correct fact. So because I refuse to convert to your beliefs, I am anti-AMD. Right.

Wait till launch, and I will make sure I reply to these posts of yours point by point. It'll be a nice, juicy discussion... Pun intended. We can take the discussion to RWT if you prefer. David always did want me to post there, but juans elder bro savantu stopped me

BTW, only you have been defensively claiming things... I've only objected to you, so far.

Guys like you/juan make AMD look so bad on new product launches by bringing false unreasonable hope to fans using pseudoscience. No sense of staying reasonable. Both extreme opposites on the curve, archenemies.

I speak as an AMD fan here - but not fanatic.

BRAD, why don't you start posting in this thread since the topics about your favorite Tejas now

Sent from HTC 10
(Opinions are own)

They are not hopes or act of faith. I saw some presentations of GF, on the Neon FPU test chip vehicle, for instance, read powerpoints on FO4 of current architecture, have studied past and current microarchitecture in details, have studied the matter at the university (including CMOS circuit design and simulation both with VHDL and PSPICE, but also analog circuit design... What do you think bjt means?), being an engineer that work in the research world, but in the medical field, still dealing with physics, though, and programming, also low level (assembler) and CUDA, for example. I know CPU and GPU architecture and I was for some time a redactor for an on-line journal, having written some technical articles on AMD and intel architectures...
I am not spitting sentences at random. I can't obviously write here a full lecture each time and often synthetize all the reasoning, and I also assume that you read my previous posts. I can't rewrite all the reasoning each post...
But obviously it's easy to say that my posts are crap. The hard part is demostrating to be right...
 

Dresdenboy

Golden Member
Jul 28, 2003
1,730
554
136
citavia.blog.de
The point is that they have access to a ryzen sample and still try to extrapolate IPC by comparing numbers from MT results.
But then again at least they are saying it outright:
At least they didn't want to leave too many traces. So they explained, that they published aggregated performance indices instead of absolute numbers to avoid this. Explicit ST analysis might have given too many clues. That's the disadvantage of testing and publishing NDA stuff.

The modules being 2T cores thing is old (published in 2009) and also a recent topic (ongoing lawsuit, which BTW has lots of technical mistakes in the claims).
http://www.freepatentsonline.com/20090024836.pdf
 

Maverick177

Senior member
Mar 11, 2016
411
70
91
:rolleyes:

On who's official statement were these estimations based on?

I'll give you a hint: 40% IPC increase over Excavator matches almost exactly the IPC of Sandy / Ivy Bridge. Not Broadwell-E's, which appears to be the case.

Spit it out.

Why are you so defensive? it's pretty clear now that Zen's IPC will be above Sandy and Ivy's.
 

laamanaator

Member
Jul 15, 2015
66
10
41
Why are you so defensive? it's pretty clear now that Zen's IPC will be above Sandy and Ivy's.
And why are you being so offensive against him? Those predictions he made were based on data available back then and they were reasonable and in line with what AMD had said at the time.
 
  • Like
Reactions: Phynaz